发表在2016年Neurocomputing。

摘要

JPEG is the most commonly used image compression standard. In practice, JPEG images are easily subject to blocking artifacts at low bit rates. To reduce the blocking artifacts, many deblocking algorithms have been proposed. However, they also introduce certain degree of blur, so the deblocked images contain multiple distortions. Unfortunately, the current quality metrics are not designed for multiply distorted images, so they are limited in evaluating the quality of deblocked images. To solve the problem, this paper presents a no-reference (NR) quality metric for deblocked images. A DeBlocked Image Database (DBID) is first built with subjective Mean Opinion Score (MOS) as ground truth. Then a NR DeBlocked Image Quality (DBIQ) metric is proposed by simultaneously evaluating blocking artifacts in smooth regions and blur in textured regions. Experimental results conducted on the DBID database demonstrate that the proposed metric is effective in evaluating the quality of deblocked images, and it significantly outperforms the existing metrics. As an application, the proposed metric is further used for automatic parameter selection in image deblocking algorithms.

结论

Image deblocking has been extensively researched for removing blocking artifacts in JPEG images. However, the quality evaluation of such deblocked images is still an open problem. In this paper, we have presented a no-reference quality model for evaluating the quality of deblocked images. Blocking artifacts in smooth regions and blur effects in textured regions are considered in the proposed model. It is a moment-based metric, where the Tchebichef moments are used to achieve: (1) block classification, (2) blocking artifact evaluation, and (3) blur evaluation. We have also built a deblocked image database DBID to compare the performances of image deblocking algorithms, and also to verify the performance of the proposed method. The experimental results have demonstrated that the proposed method is effective in evaluating the quality of deblocked images, and it significantly outperforms the state-of-the-art blocking artifact metrics, blur metrics and general-purpose NR image quality metrics. As an application of the proposed model, we have also used DBIQ for automatic parameter tuning in image deblocking algorithm, producing very promising results.
In this work, the proposed quality model is based on the Tchebichef moments of gray-scale images. However, color also affects the quality of deblocked images, so the performance of the proposed metric could be further enhanced by incorporating color information. A straightforward way to improve DBIQ is to use quaternion-type moments [51]. Furthermore, the presented work mainly focus on deblocked JPEG images. More general deblocking scenarios, e.g., deblocking loop filter in H.264/AVC, will be investigated in future work.

要点

  1. 我们讨论JPEG压缩图像的块效应。

  2. 许多去块效应方法都会引入模糊,导致图像中存在多重失真。然而,现存质量指标都只局限于单一失真(比如块效应),没有考虑模糊等其他失真。

  3. 为了解决这一问题,本文针对去块效应的图像(deblocked images),提出了一种无参考质量评价指标:NR DeBlocked Image Quality(DBIQ)。

  4. 方法核心:同时评估平滑区域的块效应,以及纹理区域的模糊程度。

  5. 具体而言,作者采用了切比雪夫矩(Tchebichef moments),同时实现了块分类、块效应评估和模糊程度评估。

  6. 本文还有建库等贡献。作者将预测的指标用于去块效应算法,发现实验结果有所提升,证明了该指标的有效性。

  7. 局限:只考虑了灰度图像;只考虑了JPEG图像。

故事背景

作者观察了借助去块效应算法[14]得到的图像,发现:去块效应图像的平滑区域容易遭受(残留)块效应影响,而纹理区域容易变模糊。

The deblocked images are contaminated by both blocking artifacts and blur. Blocking artifacts mainly affect the quality of smooth regions and blur mainly affects the quality of textured regions.

基于此观察,作者提出用离散切比雪夫矩,同时评估块效应和模糊。

本文方法(DBIQ)

DBIQ由两部分组成:

  1. 块效应指标RMB[26],是当时最好的检测块效应指标;

  2. 基于矩的模糊检测模块。

整体框图:

流程大致如下:

  1. 首先,deblocked图像被不重叠地分为\(8 \times 8\)的目标块。\(8 \times 8\)应该是JPEG编码块的尺寸。
  2. 对于每一个目标块,计算切比雪夫矩。根据非直流分量的平方和(the sum of squared non-DC moment, SSM),决定该块的类型:平滑还是纹理。

  3. 对于平滑块,我们通过RMB方法计算块效应指数。

  4. 对于纹理块,我们通过本文的方法计算模糊效应指数。作者还加入了显著性图。

  5. 两个得分通过池化,得到最终得分。

博主更关注块效应的检测,因此跑去看块效应质量评估论文啦。

Paper | No-reference Quality Assessment of Deblocked Images的更多相关文章

  1. Paper | Quality assessment of deblocked images

    目录 1. 故事 2. 失真变化 3. 方法(PSNR-B) 4. 实验 这篇文章提出了一个PSNR-B指标,旨在衡量 压缩图像的块效应强度 或 去块效应后的残留块效应强度(比较去块效应算法的优劣). ...

  2. Paper | Blind Quality Assessment Based on Pseudo-Reference Image

    目录 1. 技术细节 1.1 失真识别 1.2 得到对应的PRI并评估质量 块效应 模糊和噪声 1.3 扩展为通用的质量评价指标--BPRI 归一化3种质量评分 判断失真类型 加权求和 2. 总结 这 ...

  3. [论文笔记] Methodologies for Data Quality Assessment and Improvement (ACM Comput.Surv, 2009) (1)

    Carlo Batini, Cinzia Cappiello, Chiara Francalanci, and Andrea Maurino. 2009. Methodologies for data ...

  4. Paper | BLIND QUALITY ASSESSMENT OF COMPRESSED IMAGES VIA PSEUDO STRUCTURAL SIMILARITY

    目录 1. 技术细节 1.1 得到MDI 1.2 判别伪结构,计算伪结构相似性 2. 实验 动机:作者认为,基于块的压缩会产生一种伪结构(pseudo structures),并且不同程度压缩产生的伪 ...

  5. [论文笔记] Methodologies for Data Quality Assessment and Improvement (ACM Comput.Surv, 2009) (2)

    本篇博文主要对DMQ(S3.7)的分类进行了研读. 1. 这个章节提出了一种DQM的分类法(如下图) 由上图可见,该分类法的分类标准是对assessment & improvement阶段的支 ...

  6. Quality assessment and quality control of NGS data

    http://www.molecularevolution.org/resources/activities/QC_of_NGS_data_activity_new table of contents ...

  7. Paper | Predicting the Quality of Images Compressed After Distortion in Two Steps

    目录 1. 问题本质剖析 2. 方法细节 图像质量评估大佬AC Bovik的论文,发表在2019 TIP上. 考虑的问题:对于有参考图像质量评估(R-IQA)任务,参考图像有时是有损的.这会导致评估的 ...

  8. {ICIP2014}{收录论文列表}

    This article come from HEREARS-L1: Learning Tuesday 10:30–12:30; Oral Session; Room: Leonard de Vinc ...

  9. ITU-T G.1080 IPTV的体验质量(QoE)要求 (Quality of experience requirements for IPTV services)

    IPTV的服务质量(QoE)要求 Quality of experience requirements for IPTV services Summary This Recommendation de ...

随机推荐

  1. perl: warning: Setting locale failed. 解决

    perl: warning: Setting locale failed. perl: warning: Please check that your locale settings: LANGUAG ...

  2. golang数据结构之稀疏数组

    掌握知识: 数组的初始化和赋值 结构体的初始化和赋值 字符串和整型之间的转换以及其它的一些操作 类型断言 读取文件 写入文件 对稀疏数组进行压缩 package main import ( " ...

  3. 【JS】JS校验密码复杂度(必须包含字母、数字、特殊符号)

    #场景一:密码中必须包含大小写 字母.数字.特称字符,至少8个字符,最多30个字符: var pwdRegex = new RegExp('(?=.*[0-9])(?=.*[A-Z])(?=.*[a- ...

  4. 分词 | 双向匹配中文分词算法python实现

    本次实验内容是基于词典的双向匹配算法的中文分词算法的实现.使用正向和反向最大匹配算法对给定句子进行分词,对得到的结果进行比较,从而决定正确的分词方法. 算法描述正向最大匹配算法先设定扫描的窗口大小ma ...

  5. 最全各种系统版本的XPosed框架资料下载整理

    由于XPosed在不同安卓系统版本中对应的版本不同,给很多新手造成极大困扰,本文作者经过几番努力,给大家整理了各个版本对应的xposed框架版本以及相关资料,并附上相关下载链接,希望对大伙有所帮助. ...

  6. 【数字图像分析】基于Python实现 Canny Edge Detection(Canny 边缘检测算法)

    Canny 边缘检测算法 Steps: 高斯滤波平滑 计算梯度大小和方向 非极大值抑制 双阈值检测和连接 代码结构: Canny Edge Detection | Gaussian_Smoothing ...

  7. C# consume RestApi

    1.RestSharp. Nuget install RestSharp,Newtonsoft.Json. using System; using RestSharp; using Newtonsof ...

  8. .net 通过反射实现两个相同结构实体类的转换

    public static T2 CopyToModel<T1, T2>(T1 source) { T2 model = default(T2); PropertyInfo[] pi = ...

  9. 【LeetCode】2. 两数相加

    题目 给出两个 非空 的链表用来表示两个非负的整数.其中,它们各自的位数是按照 逆序 的方式存储的,并且它们的每个节点只能存储 一位 数字.   如果,我们将这两个数相加起来,则会返回一个新的链表来表 ...

  10. XML的互相序列化对象

    using System.Xml.Serialization; using System.IO; using System.Xml; namespace Common { public class X ...